Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    variable declarations and assignments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.32
     élé
    -0.30
     pleaſure
    -0.29
     caoutchouc
    -0.28
     vectorielles
    -0.27
     chrétiens
    -0.27
     ennemi
    -0.25
     onlyOwner
    -0.25
     souverain
    -0.25
     vôtre
    -0.25
    POSITIVE LOGITS
     パンチラ
    0.89
    <unused20>
    0.88
    <pad>
    0.87
    [@BOS@]
    0.87
    <unused43>
    0.87
    ⏔
    0.87
    <unused28>
    0.87
    <unused23>
    0.87
    <unused3>
    0.87
    <unused14>
    0.87
    Act Density 0.013%

    No Known Activations